A ready-to-use implementation of the Model Context Protocol (MCP) that extends Claude with real-time weather data capabilities.

Model Context Protocol (MCP) is an open communication framework that allows AI models like Claude to interact with external tools. This enables Claude to access real-time data, process files, and interact with external services - capabilities not available to most LLMs out of the box.

Learn more about MCP:

• MCP Official Documentation
• Getting Started with MCP
• Postmans MCP Developer Community

This repository provides:

1. Complete MCP Weather Server: A fully functional implementation that gives Claude access to real-time weather data
2. Template Code: Use as a starting point for your own MCP projects
3. Configuration Examples: Sample configuration files for connecting to Claude Desktop

The MCP Weather Server implements two primary tools:

• get-forecast: Retrieve current weather conditions and forecasts for any location by latitude/longitude
• get-alerts: Check for active weather alerts in any US state

Once connected, Claude can:

• Answer questions about current weather conditions
• Provide detailed weather forecasts
• Alert users to severe weather warnings
• Make recommendations based on weather data

• Node.js 16+ and npm
• Claude Desktop
• Basic knowledge of TypeScript/JavaScript

1. Clone this repository:

   git clone https://github.com/SterlingChin/mcp-weather-server.git
   cd mcp-weather-server

2. Install dependencies:

   npm install

3. Build the project:

   npm run build

1. Open your Claude Desktop configuration file:

   • Mac: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %AppData%\Claude\claude_desktop_config.json

2. Add the following configuration (update the path to point to your repository):

   {
     "mcpServers": {
       "weather": {
         "command": "node",
         "args": [
           "/absolute/path/to/your/mcp-weather-server/build/index.js"
         ]
       }
     }
   }

3. Restart Claude Desktop

4. Look for the hammer icon in Claude Desktop, indicating that MCP tools are available

Try asking Claude these questions:

• "What's the weather like in San Francisco right now?"
• "Are there any weather alerts in Texas today?"
• "What's the forecast for Chicago this weekend?"

├── src/
│   ├── index.ts           # Main server entry point
│   ├── tools/             # Tool implementations
│   │   ├── get-forecast.ts
│   │   └── get-alerts.ts
│   └── utils/             # Helper functions and API client
│       └── nws-api.ts
├── build/                 # Compiled JavaScript files
├── examples/              # Example code and usage patterns
├── docs/                  # Additional documentation
├── package.json
└── tsconfig.json

This repository can serve as a template for building your own MCP servers. Follow these steps:

1. Fork this repository or create a new one based on its structure
2. Replace the weather API implementation with your own service
3. Define your tools by adding new files in the src/tools directory
4. Register your tools in src/index.ts
5. Build and test your implementation

For detailed guidance, check out our step-by-step tutorial.

This server uses the National Weather Service API, which is free to use and doesn't require authentication. Other APIs you might consider integrating include:

• Dictionary/Language APIs
• News and Information APIs
• Public Data APIs
• Financial APIs

When selecting APIs for your MCP server, consider:

• Authentication requirements
• Rate limits
• Data format and parsing complexity
• Update frequency

• Claude can't find your server: Verify your configuration path and restart Claude Desktop
• API requests failing: Check your internet connection and API endpoint status
• Unexpected responses: Look at Claude Desktop logs at ~/Library/Logs/Claude/mcp*.log

Contributions are welcome! Please feel free to submit a Pull Request.

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

This project is licensed under the MIT License - see the LICENSE file for details.

Built with ❤️ using the Model Context Protocol